{"id":"https://openalex.org/W4407184801","doi":"https://doi.org/10.1109/iccv51701.2025.01534","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","display_name":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407184801","doi":"https://doi.org/10.1109/iccv51701.2025.01534"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01720","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000827309","display_name":"Nupur Kumari","orcid":"https://orcid.org/0000-0003-1799-1069"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nupur Kumari","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012540341","display_name":"Xi Yin","orcid":"https://orcid.org/0000-0002-7519-1978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi Yin","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102883508","display_name":"Jun-Yan Zhu","orcid":"https://orcid.org/0000-0001-8504-3410"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun-Yan Zhu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000623592","display_name":"Ishan Misra","orcid":"https://orcid.org/0000-0001-7708-7261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ishan Misra","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048340119","display_name":"Samaneh Azadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samaneh Azadi","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02597006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16524","last_page":"16534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.9437000155448914,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.9437000155448914,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9171000123023987,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6639770865440369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.597325325012207},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5892236232757568},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41823694109916687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3906099796295166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3776733875274658},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33113327622413635},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.27024751901626587}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6639770865440369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597325325012207},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5892236232757568},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41823694109916687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3906099796295166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3776733875274658},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33113327622413635},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27024751901626587}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.01720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01720","pdf_url":"https://arxiv.org/pdf/2502.01720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.01720","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01720","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.01720","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01720","pdf_url":"https://arxiv.org/pdf/2502.01720","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266","https://openalex.org/W4385414918"],"abstract_inverted_index":{"Customization":[0,64],"of":[1,68,71],"text-to-image":[2,54],"models":[3,55],"enables":[4],"users":[5],"to":[6,46,59,115],"insert":[7],"new":[8],"concepts":[9],"or":[10,27],"objects":[11],"and":[12,56,79,111,134],"generate":[13],"them":[14],"in":[15,75,119],"unseen":[16],"settings.":[17],"Existing":[18],"methods":[19,144],"either":[20],"rely":[21],"on":[22,30,132,145],"comparatively":[23],"expensive":[24],"test-time":[25],"optimization":[26],"train":[28,85],"encoders":[29],"single-image":[31],"datasets":[32,58],"without":[33],"multi-image":[34],"supervision,":[35],"which":[36],"can":[37],"limit":[38],"image":[39,112],"quality.":[40],"We":[41,50],"propose":[42,104],"a":[43,61,98],"simple":[44],"approach":[45],"address":[47],"these":[48],"challenges.":[49],"first":[51],"leverage":[52],"existing":[53,142],"3D":[57],"create":[60],"high-quality":[62],"Synthetic":[63],"Dataset":[65],"(SynCD)":[66],"consisting":[67],"multiple":[69],"images":[70,96],"the":[72,136],"same":[73],"object":[74],"different":[76],"lighting,":[77],"backgrounds,":[78],"poses.":[80],"Using":[81],"this":[82],"dataset,":[83],"we":[84,103,125],"an":[86,105],"encoder-based":[87,129,143],"model":[88],"that":[89,108,127],"incorporates":[90],"fine-grained":[91],"visual":[92],"details":[93],"from":[94],"reference":[95],"via":[97],"shared":[99],"attention":[100],"mechanism.":[101],"Finally,":[102],"inference":[106,138],"technique":[107],"normalizes":[109],"text":[110],"guidance":[113],"vectors":[114],"mitigate":[116],"overexposure":[117],"issues":[118],"sampled":[120],"images.":[121],"Through":[122],"extensive":[123],"experiments,":[124],"show":[126],"our":[128],"model,":[130],"trained":[131],"SynCD,":[133],"with":[135],"proposed":[137],"algorithm,":[139],"improves":[140],"upon":[141],"standard":[146],"customization":[147],"benchmarks.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}